ductuan024
commited on
Commit
·
6786bd4
1
Parent(s):
0e2c65f
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<h1>BERT for Vietnamese Law</h1>
|
2 |
+
|
3 |
+
Apply for Task 1: Legal Document Retrieval on <a href="https://www.jaist.ac.jp/is/labs/nguyen-lab/home/alqac-2021/">ALQAC 2021</a> dataset
|
4 |
+
|
5 |
+
The model achieved 0.80 on the leaderboard, (1st place score is 0.88)
|
6 |
+
|
7 |
+
We use <a href="https://huggingface.co/NlpHUST/vibert4news-base-cased">vibert4news</a> as based model and fine-tune on our own Vietnamese law dataset.
|
8 |
+
|
9 |
+
We use word sentencepiece, use basic bert tokenization and same config with bert base with lowercase = False.
|
10 |
+
|